Abstract: Systems and methods for predicting one or more field values using machine learning in a knowledge engineering (KE) data model are disclosed. An example method may include identifying a first field in the KE data model which lacks a value and for which one or more machine learning models are defined, the first field being associated with one or more dependent field, determining that each dependent field of the first field has a corresponding value in the KE data model, executing each of the one or more machine learning models to predict one or more values for the first field, selecting one of the one or more predicted values as the representative value of the first field, identifying one or more further fields in the KE data model for which the first field is a dependent field, none of the one or more further fields defining any machine learning models, and calculating values for one or more further fields based at least in part on the representative value of the first field.

Abstract: Computer-implemented systems, methods and articles for generating an error report listing errors identified in the computerized preparation of a payroll tax form. The system includes a computing device, a data store, and a payroll tax form software application executable by the computing device. The payroll tax form software includes a payroll calculation engine, an error check engine, and one or more error graph(s). Each error graph includes a plurality of interconnected nodes configured to utilize tax data and calculated payroll data to identify errors. The calculation engine is configured to read tax data from the shared data store, perform payroll calculation operations, and write calculated payroll data to the shared data store. The error check engine is configured to read the tax data and payroll data and process the error graph(s) to identify errors and generate an error report listing the errors and/or explanations of the errors.

Abstract: Computer-implemented systems, methods and articles for identifying errors in the computerized preparation of a payroll tax form to be submitted to a tax agency. The system includes a computing device, a data store, and a payroll tax form preparation software application executable by the computing device. The payroll tax form preparation software includes a payroll calculation engine, an error check engine, and a schema error module having a plurality of error rules in the form of meta data generated from tax agency schema requirements. The calculation engine is configured to read tax data from the shared data store, perform payroll calculation operations, and write calculated payroll data to the shared data store. The error check engine is configured to read the tax data and payroll data and check the data against the error rules to identify errors. An explanation engine may generate narrative explanations of the errors.

Abstract: Computer-implemented systems, methods and articles for identifying errors in the computerized preparation of a payroll tax form to be submitted to a tax agency. The system includes a computing device, a data store, and a payroll tax form preparation software application executable by the computing device. The payroll tax form preparation software includes a payroll calculation engine, an error check engine, and one or more error graph(s). Each error graph includes a plurality of interconnected nodes configured to utilize tax data and calculated payroll data to identify errors. The calculation engine is configured to read tax data from the shared data store, perform payroll calculation operations, and write calculated payroll data to the shared data store. The error check engine is configured to read the tax data and payroll data and process the error graph(s) to identify errors. An explanation engine may generate narrative explanations of the errors.